Article Per Year (5 Year)
p-Index From 2020 - 2025
3.346
P-Index
This Author published in this journals
All Journal Indonesian Journal of Electronics and Instrumentation Systems Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Proceedings of KNASTIK Jurnal sistem informasi, Teknologi informasi dan komputer JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI Bulletin of Computer Science Research Jurnal Pengabdian kepada Masyarakat Bina Darma Algoritme Jurnal Mahasiswa Teknik Informatika Arcitech: Journal of Computer Science and Artificial Intelligence MDP Student Conference
Wijang Widhiarso
Universitas Multi Data Palembang
Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Languange, Linguistic, Communication & Media Library & Information Science Mathematics Other

Published : 25 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 25 Documents
Search

 1   2   3 
Klasifikasi Citra Sampah Botol Plastik Jenis HDPE dan PET Menggunakan Algoritma YOLOv7 Purwasih, Opita; Widhiarso, Wijang; Muhammad Rizky Pribadi
Bulletin of Computer Science Research Vol. 5 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i4.654

Abstract

The classification of plastic bottle waste, particularly High Density Polyethylene (HDPE) and Polyethylene Terephthalate (PET), remains a challenge in recycling processes due to their similar visual characteristics. Misclassification can lead to a decline in recycled material quality and economic losses in the waste management industry. This research aims to develop an automated image-based classification system to distinguish between HDPE and PET plastic waste using the You Only Look Once version 7 (YOLOv7) object detection algorithm. The dataset consists of plastic bottle images in various physical conditions, annotated with bounding boxes to support model training. The data were split into 70% for training, 20% for validation, and 10% for testing. The best performance was achieved with a batch size of 16 and 100 training epochs, resulting in a precision of 93.9%, recall of 91.6%, and a mean Average Precision (mAP@0.5) of 96.5%. The model demonstrated the ability to accurately classify both types of plastic bottles, even when objects were deformed. These results suggest that the YOLOv7 algorithm is highly capable for implementation in image-based waste classification systems, enhancing sorting efficiency and supporting more sustainable plastic waste management practices.
Klasifikasi Otomatis Tingkat Kerusakan Retak Bangunan pada Citra Digital Menggunakan MobileNetV2 dan Augmentasi Data Ricky Putra Sardika; Widhiarso, Wijang
Arcitech: Journal of Computer Science and Artificial Intelligence Vol. 5 No. 1 (2025): June 2025
Publisher : Institut Agama Islam Negeri (IAIN) Curup

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29240/arcitech.v5i1.13938

Abstract

Crack detection in buildings is a crucial step in maintaining structural integrity at an early stage and preventing further damage. This study aims to improve the accuracy of crack severity classification in digital images by applying five on-the-fly data augmentation techniques (flip, rotate, zoom, translation, and contrast) combined with the MobileNetV2 architecture. The augmentation techniques are performed dynamically during the training process without storing the transformed images, making the process more efficient in terms of storage, computation time, and adaptability to data variations. This study utilized a dataset of 900 images and achieved a classification accuracy of 93%, which is higher than the previous approach using MobileNetV1 with offline augmentation that only reached 89%. Previous research was limited to static augmentation approaches and less efficient CNN architectures. This study addresses those limitations by integrating dynamic augmentation and a lightweight architecture. It contributes to enhancing the efficiency and accuracy of crack image classification models in the context of limited data and low-computation systems, with strong potential for implementation in automated detection systems on mobile or edge computing devices.
CLASSIFICATION OF PNEUMONIA USING K-NEAREST NEIGHBOR METHOD WITH GLCM EXTRACTION Wijaya, Chandra; Irsyad, Hafiz; Widhiarso, Wijang
Jurnal Algoritme Vol 1 No 1 (2020): Oktober 2021 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1864.245 KB) | DOI: 10.35957/algoritme.v1i1.431

Abstract

Pneumonia is an inflammatory parenchymal disease caused by various microorganisms, including bacteria, micro bacteria, fungi, and viruses. This study used an X-ray to find out whether or not there was pneumonia. The objective of this study was to classify the X-ray results whether or not there was pneumonia in a fast and precise way through a program to produce good accuracy. The classification method used in this study were K-Nearest Neighbor (KNN) and Gray Level Co-Occurrence (GLCM) for the extraction method. There are several stages before being classified, namely cropping, resizing, contrast stretching, and thresholding. The results showed that the best accuracy per class was 66.20% for K = 5.
Klasterisasi Topik Skripsi Informatika dengan Metode DBSCAN Khan, Zicola Vladimir VIky; Alamsyah, Derry; Widhiarso, Wijang
Jurnal Algoritme Vol 3 No 1 (2022): Oktober 2022 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v3i1.3337

Abstract

This research analyzed 176 Palembang public universities’ students’ theses which were published in 2020. The data was analyzed by conducting text processing and extraction with TF-IDF feature by using two scenarios, the reduced feature value and the unreduced one, with SVD method. In each scenario, three metrics, cosine, euclidean, and, manhattan were used, which generated six scenarios in total. The result found that the best quality of cluster which was measured by silhouette coefficient comes from metric cosine and reducted by SVD with the silhouette coefficient value of 0.88382763, intracluster value of 0.08688583, and intercluster value of 0.74671096. Therefore, the cluster quality value of the reducted feature is the best among all metrics. In addition, the use of DBSCAN method showed a positive correlation between epsilon and intracluster with the value of 0.97669, and also showed a negative correlation between epsilon and silhouette with the value of 0.9789.
Klasifikasi Pengenalan Wajah Untuk Mengetahui Jenis Kelamin Menggunakan Metode Convolutional Neural Network SATRIAWAN, MUHAMMAD AKBAR; WIDHIARSO, WIJANG
Jurnal Algoritme Vol 4 No 1 (2023): Oktober 2023 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v4i1.6095

Abstract

The face is the component that is most easily recognized and is often the center of attention of other people in the human body. There are often difficulties in distinguishing and analyzing large numbers of facial images manually due to the large number of similarities between males and females, which slows down the process of gender identification. This research was made to fix this problem by using the CNN method. The dataset used is 2280 images consisting of train, valid and test. The research process includes data pre-processing, model initialization, model training, hyperparameter validation and adjustment, and model performance evaluation. The test results show an increase in accuracy and a decrease in loss as training iterations increase. In this study, results were obtained with an accuracy rate of 92%, which shows the effectiveness of using a Convolutional Neural Network (CNN) with the ResNet-50 architecture in processing and classifying male and female facial images.
Co-Authors Ahmad Farisi Andres, Yohanes Asyraq, Cerwyn Cendy Prakarsah Chandra Wijaya Dafid Dafid Derry Alamsyah Edi Winarko Edo Renaldo Ericco Andreas Ervina Patricia Arifin Hafiz Irsyad Kersen Kersen Khan, Zicola Vladimir VIky Kurniawan, Wiji Manalu, Josua Michael Michael Muhammad Irfan Muhammad Rachmadi, Muhammad Muhammad Rizky Pribadi Purwasih, Opita Ricky Putra Sardika Sardika, Ricky Putra SATRIAWAN, MUHAMMAD AKBAR Sri Hartati Usman Usman Vera Nofita Verren Oktaviana Wiwik Handayani Yuda, Andika Dirma